Skip to content

For developers

Internal tools from your coding agent, or your editor. Your call.

Install the ToolJet plugin and your agent builds real ToolJet apps: pages, queries, components and permissions, against your actual data sources. Drop into JavaScript or Python when the visual layer is not enough. Nothing you build is a throwaway.

  • Admin panels over Postgres
  • Approval flows with audit trails
  • Ops dashboards from your warehouse
Example Claude Code session · illustrative

Build a refund approvals app on the orders table in our Postgres. Support agents request, finance approves over $500, every decision logged.

  1. list_datasourcesfound prod-postgres (read/write), stripe
  2. get_datasource_query_schemaorders, refunds, users
  3. create_appRefund approvals · 2 pages · 7 components
  4. add_querieslistPending, approveRefund, logDecision
  5. manage_app_permissionssupport: request · finance: approve
  6. lint_app_spec0 errors · 1 warning (empty state)

App created in development. Open in the editor or promote to staging.

40,000+stars on the open-source core
AICPA SOCISO 27001
SOC 2 Type IIISO 27001 and GDPR · Visit the trust centre
Your infrastructureCloud, VPC, on-premise or air-gapped
100+ connectorsplus any REST or gRPC endpoint

The ToolJet plugin

Your agent gets the app model, not a guessed config

The plugin exposes ToolJet's own contracts to your coding agent: data source schemas, component catalogue, query lifecycles and permissions. The build workflow can validate planned app changes before applying them, then check the saved result. It runs on your agent's subscription, not ToolJet AI credits.

  • Works with Claude Code, Codex, Cursor, GitHub Copilot and any MCP client
  • Agent work lands in development; promotion follows your normal release process
  • Everything the agent builds stays editable on the canvas
  • Claude Code
  • Codex
  • Cursor
  • GitHub Copilot
  • Grok Build
From token to app
# 1. Create a personal access token in ToolJet (Profile Settings → Personal access tokens)
# 2. Add the ToolJet MCP server to your agent: docs.tooljet.ai/docs/build-with-ai/mcp/setup/
# 3. Ask for an app
> Build an on-call rota app on the engineers table in prod-postgres

list_datasources        → prod-postgres, pagerduty
create_app              → On-call rota · 2 pages · 9 components
manage_app_permissions  → platform-eng: edit · everyone: view
lint_app_spec           → 0 errors
How the ToolJet plugin works

Talks to what you already run

  • PostgreSQL
  • MySQL
  • MongoDB
  • Snowflake
  • REST API
  • Stripe
  • Slack
  • BigQuery
Browse all integrations

What developers ship with ToolJet

The tools that never make the roadmap, without a React project each time.

Admin panels

CRUD over production tables with row-level rules, search, bulk actions and an audit trail, in an afternoon.

Approval and review queues

Multi-step approvals with role-gated actions, Slack or email notifications and every decision recorded.

Ops and on-call dashboards

Live views over Postgres, Snowflake or your APIs, with drill-downs and actions wired to queries.

Support and success tooling

Customer lookups joining your database, Stripe and Zendesk, with guarded write actions.

Scheduled and event-driven workflows

On Self-hosted, build webhook, scheduled or app-triggered workflows with JavaScript logic, data-source nodes and run logs.

Custom components when you need them

Bring your own React component for the one widget the catalogue does not cover; everything else stays declarative.

How it fits your workflow

  1. 01

    Build where you are

    From your agent through the plugin, or on the canvas. Both write to the same application model, so a teammate can pick up either way.

  2. 02

    Code where it earns its place

    JavaScript and Python queries in apps, with custom JavaScript logic in Self-hosted workflows. Custom components for the rest.

  3. 03

    Promote like software

    Development, staging and production environments with environment-scoped credentials, Git sync and version history with rollback.

  4. 04

    Ship without a permissions ticket

    Apps inherit workspace SSO and roles. Set page, component, query and row-level access as part of the build, not after.

In production

Teams already running on ToolJet

Built in, not bolted on

The plumbing you would otherwise write yourself

Authentication, authorisation, secrets, environments and audit come with the platform, so an internal tool does not need its own auth middleware or deployment pipeline.

Auth you do not maintain

SAML, OIDC and LDAP with directory groups mapped to roles and SCIM provisioning.

Permissions to the query

Workspace, app, page, component and query-level access, plus row-level security where the data needs it.

Credentials stay server-side

Data source secrets never reach the browser or the agent; queries run through ToolJet with environment-scoped credentials.

Release you control

Git sync, versioned releases, rollback and separate environments. Agent changes wait in development until you promote them.

Security and governance features vary by plan. Workflows and Agent Builder are available on Self-hosted only; BYOK is a Self-hosted Enterprise add-on. Compare plan availability.

Two ways to get there

Build it yourself, or bring our engineers in

Self-serve

Your team, your pace

Start free. Describe the tool, refine it on the canvas, and ship it under your own access rules. Start with one app, then test it with your team before rolling it out.

Start free

Professional services

Forward-deployed engineers, embedded with your team

When the timeline is fixed or the process is tangled, our engineers build alongside you: scoped delivery, production-ready apps, and knowledge transfer so your team owns the result.

Talk about a project

Questions developers ask before they start

How is this different from having my agent generate a React app?

The agent builds against ToolJet's application model, not free-form code: components, queries, events and permissions your team can open in the visual editor afterwards. You skip auth, hosting, secrets and deployment for each tool, and the result is maintainable by whoever is on the team next year.

Can I write real code?

Yes. JavaScript and Python queries in apps, with custom JavaScript logic in Self-hosted workflows. You can also build custom React components for anything the catalogue does not cover. Code is the escape hatch, not the starting point.

Does the agent get access to our databases?

The agent can inspect schemas and run queries through ToolJet when the connecting user has permission. Query results can therefore be visible to the agent and its model provider. Data source credentials stay in ToolJet. Use a workspace token with appropriate access and review queries before running them.

How do releases work?

Apps move through development, staging and production with environment-specific credentials. Git sync keeps app definitions in your repository, and version history lets you roll back. Agent-built changes land in development.

Can I self-host it?

Yes. Docker, Kubernetes, Helm and OpenShift, in your VPC, on-premise or air-gapped. The Community Edition is open source under AGPL-3.0; the MCP server is MIT-licensed.

Build the next internal tool from the agent you already have open

Install the ToolJet plugin, point it at your workspace and describe the app. Or start on the canvas, free.

Page updated